diff --git a/aws/amazon-bedrock-agentcore/travel_assistant/.gitignore b/aws/amazon-bedrock-agentcore/travel_assistant/.gitignore
new file mode 100644
index 0000000..a5cbf6c
--- /dev/null
+++ b/aws/amazon-bedrock-agentcore/travel_assistant/.gitignore
@@ -0,0 +1,66 @@
+# Environment variables and secrets
+.env
+.env.local
+.env.*.local
+*.key
+*.pem
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+venv/
+env/
+ENV/
+.venv
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+.DS_Store
+
+# Logs
+*.log
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+
+# Bedrock AgentCore
+.bedrock_agentcore/
+.bedrock_agentcore.yaml
+
+# Screenshots (if generated)
+screenshots/
+*.png
+!docs/*.png
+
+# Temporary files
+tmp/
+temp/
+*.tmp
+
diff --git a/aws/amazon-bedrock-agentcore/travel_assistant/QUICKSTART.md b/aws/amazon-bedrock-agentcore/travel_assistant/QUICKSTART.md
new file mode 100644
index 0000000..0011ffe
--- /dev/null
+++ b/aws/amazon-bedrock-agentcore/travel_assistant/QUICKSTART.md
@@ -0,0 +1,133 @@
+# Quick Start Guide
+
+Get the Travel Assistant Agent running in 5 minutes!
+
+## Prerequisites Checklist
+
+- [ ] Python 3.11+ installed
+- [ ] AWS Account with Bedrock access
+- [ ] AWS CLI configured (`aws configure`)
+- [ ] Bedrock AgentCore SDK installed (`pip install bedrock-agentcore`)
+- [ ] (Optional) AgentCore CLI access for deployment
+
+## Step 1: Get API Keys
+
+### Tavily API Key (Required)
+1. Visit [https://tavily.com](https://tavily.com)
+2. Sign up and get your API key
+3. Save it for the next step
+
+### Elastic API Key (Optional - for observability)
+1. Visit [https://cloud.elastic.co](https://cloud.elastic.co)
+2. Create a serverless deployment
+3. Go to Management > API Keys > Create API Key
+4. Save the key and OTLP endpoint
+
+## Step 2: Install Dependencies
+
+```bash
+pip install -r requirements.txt
+```
+
+## Step 3: Configure Environment
+
+```bash
+# Option 1: Export directly
+export TAVILY_API_KEY="your-key-here"
+
+# Option 2: Create .env file
+cp env.example .env
+# Edit .env with your values
+```
+
+## Step 4: Launch the Agent
+
+Choose one of the following methods:
+
+**Note**: Requires access to the `agentcore` CLI tool from Bedrock AgentCore Starter Toolkit.
+
+1. Set AWS credentials (required before running agentcore):
+```bash
+export AWS_ACCESS_KEY_ID=your-aws-access-key-id
+export AWS_SECRET_ACCESS_KEY=your-aws-secret-access-key
+export AWS_REGION=us-east-1
+export AWS_PROFILE=your-aws-profile  # Optional
+```
+
+2. Configure the entrypoint:
+```bash
+agentcore configure --entrypoint claudeserver.py --name travel_assistant_quickstart
+```
+
+3. Launch with minimal config:
+```bash
+agentcore launch --env TAVILY_API_KEY="your-tavily-key"
+```
+
+4. Or launch with full observability:
+```bash
+agentcore launch \
+  --env OTEL_EXPORTER_OTLP_ENDPOINT="https://your-id.ingest.region.cloud.elastic.co:443" \
+  --env OTEL_EXPORTER_OTLP_HEADERS="Authorization=ApiKey your-elastic-key" \
+  --env OTEL_EXPORTER_OTLP_PROTOCOL="http/protobuf" \
+  --env OTEL_METRICS_EXPORTER="otlp" \
+  --env OTEL_TRACES_EXPORTER="otlp" \
+  --env OTEL_LOGS_EXPORTER="otlp" \
+  --env OTEL_RESOURCE_ATTRIBUTES="service.name=travel_assistant_quickstart,service.version=1.0.0" \
+  --env AGENT_OBSERVABILITY_ENABLED="true" \
+  --env DISABLE_ADOT_OBSERVABILITY="true" \
+  --env TAVILY_API_KEY="your-tavily-key"
+```
+
+## Step 5: Test It!
+
+**Quick test:**
+```bash
+agentcore invoke '{"prompt":"Best places to visit in Netherlands"}'
+```
+
+**Using test scripts:**
+
+Fast search (5-10 seconds):
+```bash
+./invoke.sh
+```
+
+Delayed search (120+ seconds):
+```bash
+./invoke_india_best_places.sh
+```
+
+## Expected Output
+
+You should see:
+- Search results from both Tavily and DuckDuckGo
+- Travel recommendations with descriptions
+- Source URLs for more information
+
+## Step 6: Verify Observability (If Configured)
+
+1. Go to your Elastic Cloud deployment
+2. Navigate to **Observability** > **APM**
+3. Find the `travel_assistant` service
+4. View traces, metrics, and logs
+
+## Troubleshooting
+
+**"TAVILY_API_KEY not set"**
+- Make sure you exported the variable or passed it via `--env`
+
+**"Bedrock Access Denied"**
+- Enable Claude 3.5 Sonnet model in AWS Bedrock console
+- Check IAM permissions
+
+**"Timeout Error"**
+- Increase timeout settings
+- For India search, this is expected (120s delay)
+
+**No Observability Data**
+- Verify OTLP endpoint is correct
+- Check Elastic API key permissions
+- Ensure all OTEL_* variables are set
+
+
diff --git a/aws/amazon-bedrock-agentcore/travel_assistant/README.md b/aws/amazon-bedrock-agentcore/travel_assistant/README.md
new file mode 100644
index 0000000..4ca18ee
--- /dev/null
+++ b/aws/amazon-bedrock-agentcore/travel_assistant/README.md
@@ -0,0 +1,341 @@
+# Travel Assistant Agent
+
+A multi-search travel recommendation agent built with AWS Bedrock AgentCore, Strands, and multiple search providers. This agent compares search latency and results between **Tavily** and **DuckDuckGo** search engines to provide comprehensive travel recommendations.
+
+## Overview
+
+This travel assistant agent demonstrates:
+
+- **Dual Search Engine Integration**: Simultaneously uses Tavily and DuckDuckGo to compare search performance and results
+- **Latency Comparison**: Measures and compares response times between different search providers
+- **Custom Tool with Delay**: Includes a special `country_specific_search` tool with intentional delay for testing long-running operations
+- **Observability**: Full integration with Elastic Observability for monitoring and tracing
+- **AWS Bedrock Integration**: Uses Claude 3.5 Sonnet via AWS Bedrock for intelligent travel recommendations
+
+## Features
+
+### Search Tools
+
+1. **web_search (Tavily)**: Fast, AI-optimized search using Tavily Search API
+2. **web_search_ddg (DuckDuckGo)**: Traditional web search using DuckDuckGo
+3. **country_specific_search**: Specialized tool for India travel searches with 120-second delay
+
+### Country-Specific Search Logic
+
+The `country_specific_search` tool includes a **120-second delay** before executing. This is designed to:
+
+- **Test Long-Running Operations**: Simulate real-world scenarios where certain operations take extended time
+- **Observability Testing**: Validate that tracing and monitoring correctly handle long-duration spans
+- **Timeout Handling**: Test the agent's behavior with slow-responding tools
+- **User Experience Testing**: Demonstrate how to handle operations that require significant wait times
+
+The delay is intentional and serves as a testing mechanism for production-grade agent deployments where some operations may naturally take longer.
+
+## Architecture
+
+```
+┌─────────────────┐
+│  AgentCore      │
+│  Runtime        │
+└────────┬────────┘
+         │
+         v
+┌─────────────────┐     ┌──────────────┐
+│  Strands Agent  │────>│  Claude 3.5  │
+│                 │     │  (Bedrock)   │
+└────────┬────────┘     └──────────────┘
+         │
+         ├────> Tavily Search (Fast)
+         ├────> DuckDuckGo Search (Comparison)
+         └────> Country-Specific Search (Delayed)
+```
+
+## Prerequisites
+
+- AWS Account with Bedrock access
+- Python 3.11+
+- AgentCore CLI installed
+
+## Setup Instructions
+
+### 1. Install AgentCore SDK
+
+```bash
+pip install bedrock-agentcore
+```
+
+**Note**: The `agentcore` CLI command requires the Bedrock AgentCore Starter Toolkit, which may need to be installed separately or accessed through AWS preview programs.
+
+### 2. Obtain Tavily API Key
+
+1. Visit [https://tavily.com](https://tavily.com)
+2. Sign up for a free account
+3. Navigate to your dashboard
+4. Copy your API key from the API Keys section
+5. Free tier includes 1,000 searches per month
+
+### 3. Set Up Elastic Observability (Optional but Recommended)
+
+#### Create Elastic Serverless Account
+
+1. Go to [https://cloud.elastic.co](https://cloud.elastic.co)
+2. Click "Start free trial" or "Sign up"
+3. Choose "Serverless" deployment option
+4. Select your cloud provider and region
+5. Create your deployment (usually takes 1-2 minutes)
+
+#### Obtain Elastic API Key
+
+1. Once your Elastic deployment is ready, navigate to your deployment
+2. Go to **Management** > **Stack Management** > **API Keys**
+3. Click **"Create API Key"**
+4. Give it a name (e.g., "AgentCore Observability")
+5. Set appropriate privileges or use default
+6. Click **Create API Key**
+7. **Copy and save** the API key immediately (you won't be able to see it again)
+
+#### Get OTLP Endpoint
+
+1. In your Elastic deployment, go to **Observability** > **APM**
+2. Click **"Add data"**
+3. Select **"OpenTelemetry"**
+4. Copy the **OTLP Endpoint URL** displayed (format: `https://<deployment-id>.ingest.<region>.cloud.elastic.co:443`)
+
+### 4. Configure AWS Credentials
+
+Ensure your AWS credentials are configured. You can use AWS CLI configuration:
+
+```bash
+aws configure
+```
+
+Or set environment variables directly (required for agentcore CLI):
+
+```bash
+export AWS_ACCESS_KEY_ID=your-aws-access-key-id
+export AWS_SECRET_ACCESS_KEY=your-aws-secret-access-key
+export AWS_REGION=us-east-1
+export AWS_PROFILE=your-aws-profile  # Optional, if using AWS profiles
+```
+
+**Note**: The agentcore CLI requires these environment variables to be set before running configuration and deployment commands.
+
+### 5. Install Dependencies
+
+```bash
+pip install -r requirements.txt
+```
+
+### 6. Configure AgentCore (CLI Method)
+
+**If you have access to the `agentcore` CLI**, first set your AWS credentials:
+
+```bash
+# Set AWS credentials for AgentCore
+export AWS_ACCESS_KEY_ID=your-aws-access-key-id
+export AWS_SECRET_ACCESS_KEY=your-aws-secret-access-key
+export AWS_REGION=us-east-1
+export AWS_PROFILE=your-aws-profile  # Optional, if using AWS profiles
+```
+
+Then configure the entrypoint:
+
+```bash
+agentcore configure --entrypoint claudeserver.py --name travel_assistant_quickstart
+```
+
+This command:
+- Sets `claudeserver.py` as the agent entrypoint
+- Names the agent `travel_assistant_quickstart`
+- Configures the runtime environment
+- Creates `.bedrock_agentcore.yaml` configuration file (excluded from git)
+
+## Configuration
+
+### Environment Variables
+
+Create a `.env` file or export the following:
+
+```bash
+# Required
+export TAVILY_API_KEY="your-tavily-api-key-here"
+
+# Optional - AWS Configuration
+export AWS_DEFAULT_REGION="us-east-1"
+export BEDROCK_MODEL_ID="us.anthropic.claude-3-5-sonnet-20240620-v1:0"
+
+# Optional - Observability (Elastic)
+export OTEL_EXPORTER_OTLP_ENDPOINT="https://your-deployment-id.ingest.region.cloud.elastic.co:443"
+export OTEL_EXPORTER_OTLP_HEADERS="Authorization=ApiKey your-elastic-api-key-here"
+export OTEL_EXPORTER_OTLP_PROTOCOL="http/protobuf"
+export OTEL_METRICS_EXPORTER="otlp"
+export OTEL_TRACES_EXPORTER="otlp"
+export OTEL_LOGS_EXPORTER="otlp"
+export OTEL_RESOURCE_ATTRIBUTES="service.name=travel_assistant,service.version=1.0.0,deployment.environment=production"
+export AGENT_OBSERVABILITY_ENABLED="true"
+export DISABLE_ADOT_OBSERVABILITY="true"
+
+# Optional - Logging
+export AGENT_RUNTIME_LOG_LEVEL="INFO"
+```
+
+## Launching the Agent
+
+**Important**: Make sure you've run `agentcore configure --entrypoint claudeserver.py --name travel_assistant_quickstart` before launching (see step 6 above).
+
+### Basic Launch (Without Observability)
+
+```bash
+agentcore launch --env TAVILY_API_KEY="your-tavily-api-key"
+```
+
+### Full Launch (With Elastic Observability)
+
+```bash
+agentcore launch \
+  --env OTEL_EXPORTER_OTLP_ENDPOINT="https://<your-deployment-id>.ingest.<region>.cloud.elastic.co:443" \
+  --env OTEL_EXPORTER_OTLP_HEADERS="Authorization=ApiKey <your-elastic-api-key>" \
+  --env OTEL_EXPORTER_OTLP_PROTOCOL="http/protobuf" \
+  --env OTEL_METRICS_EXPORTER="otlp" \
+  --env OTEL_TRACES_EXPORTER="otlp" \
+  --env OTEL_LOGS_EXPORTER="otlp" \
+  --env OTEL_RESOURCE_ATTRIBUTES="service.name=travel_assistant_quickstart,service.version=1.0.0,deployment.environment=production" \
+  --env AGENT_OBSERVABILITY_ENABLED="true" \
+  --env DISABLE_ADOT_OBSERVABILITY="true" \
+  --env TAVILY_API_KEY="<your-tavily-api-key>"
+```
+
+**Note**: Replace placeholders (`<...>`) with your actual credentials.
+
+## Testing the Agent
+
+### Regular Search (Netherlands Example)
+
+This will use both Tavily and DuckDuckGo search engines:
+
+```bash
+./invoke.sh
+```
+
+Or manually:
+
+```bash
+START=$(date +%s)
+agentcore invoke '{"prompt":"Best places to visit in Netherlands"}'
+END=$(date +%s)
+echo "Time taken: $((END - START)) seconds"
+```
+
+### Delayed Search (India Example)
+
+This triggers the `country_specific_search` tool with 120-second delay:
+
+```bash
+./invoke_india_best_places.sh
+```
+
+Or manually:
+
+```bash
+START=$(date +%s)
+agentcore invoke '{"prompt":"Best places to visit in India"}'
+END=$(date +%s)
+echo "Time taken: $((END - START)) seconds"
+```
+
+**Expected behavior**: The India search will take approximately 120+ seconds due to the intentional delay in the `country_specific_search` tool.
+
+## Comparing Search Latency
+
+The agent is designed to compare latency between:
+
+1. **Tavily Search** (`web_search`): Typically faster, optimized for AI applications
+2. **DuckDuckGo Search** (`web_search_ddg`): Traditional web search, may vary in speed
+
+The agent will call both search engines for most queries, allowing you to observe:
+- Response time differences
+- Result quality differences
+- API reliability
+
+You can monitor these metrics in Elastic Observability if configured.
+
+## Project Structure
+
+```
+travel_assistant/
+├── claudeserver.py                 # Main agent implementation
+├── requirements.txt                # Python dependencies
+├── .gitignore                      # Git ignore patterns
+├── README.md                       # This file
+├── QUICKSTART.md                   # 5-minute setup guide
+├── env.example                     # Environment template
+├── invoke.sh                       # Test script (Netherlands)
+├── invoke_india_best_places.sh     # Test script (India with delay)
+└── launch_with_observability.sh    # Full launch script with observability
+```
+
+## Key Components
+
+### claudeserver.py
+
+- **Tools**: Three search tools (Tavily, DuckDuckGo, Country-specific)
+- **Agent**: Strands Agent with Claude 3.5 Sonnet
+- **Telemetry**: OpenTelemetry integration for observability
+- **Entrypoint**: BedrockAgentCore app entrypoint
+
+
+## Observability
+
+When Elastic Observability is configured, you can monitor:
+
+- **Traces**: Full execution traces including tool calls
+- **Metrics**: Performance metrics, latency distributions
+- **Logs**: Structured logs from the agent
+- **Spans**: Individual operation timing (search calls, LLM calls, etc.)
+
+Access your Elastic deployment to view:
+- APM (Application Performance Monitoring)
+- Service maps
+- Trace timelines
+- Error tracking
+
+
+## Troubleshooting
+
+### Common Issues
+
+1. **agentcore: command not found**
+   - Install the Bedrock AgentCore Starter Toolkit: `pip install bedrock-agentcore-starter-toolkit`
+   - Verify installation: `agentcore --help`
+
+2. **Tavily API Key Error**
+   - Ensure `TAVILY_API_KEY` is set correctly
+   - Verify your API key is active at tavily.com
+
+3. **AWS Bedrock Access Denied**
+   - Enable Bedrock model access in AWS Console
+   - Verify IAM permissions for Bedrock
+
+4. **Observability Not Working**
+   - Check Elastic OTLP endpoint is accessible
+   - Verify API key has correct permissions
+   - Ensure OTEL environment variables are set
+
+5. **Timeout on India Search**
+   - This is expected! The tool has a 120-second delay
+   - Ensure your timeout settings are >= 130 seconds
+
+
+## Security Notes
+
+- Never commit API keys or credentials
+- Use environment variables for sensitive data
+- Rotate API keys regularly
+- Use AWS Secrets Manager for production deployments
+
+## Support
+
+For issues or questions:
+- AWS Bedrock AgentCore: [AWS Documentation](https://docs.aws.amazon.com/bedrock/)
+- Tavily API: [Tavily Documentation](https://docs.tavily.com/)
+- Elastic Observability: [Elastic Documentation](https://www.elastic.co/guide/)
diff --git a/aws/amazon-bedrock-agentcore/travel_assistant/claudeserver.py b/aws/amazon-bedrock-agentcore/travel_assistant/claudeserver.py
new file mode 100644
index 0000000..e1c35aa
--- /dev/null
+++ b/aws/amazon-bedrock-agentcore/travel_assistant/claudeserver.py
@@ -0,0 +1,248 @@
+import os
+import logging
+import time
+from bedrock_agentcore.runtime import BedrockAgentCoreApp
+from strands import Agent, tool
+from strands.models import BedrockModel
+from strands.telemetry import StrandsTelemetry
+from tavily import TavilyClient
+from duckduckgo_search import DDGS
+
+# Optional OpenTelemetry imports for custom resource configuration
+try:
+    from opentelemetry.sdk.resources import Resource
+    from opentelemetry.sdk.trace import TracerProvider
+    from opentelemetry import trace as trace_api
+    from opentelemetry import propagate
+    from opentelemetry.baggage.propagation import W3CBaggagePropagator
+    from opentelemetry.propagators.composite import CompositePropagator
+    from opentelemetry.trace.propagation.tracecontext import (
+        TraceContextTextMapPropagator,
+    )
+
+    OTEL_AVAILABLE = True
+except ImportError:
+    OTEL_AVAILABLE = False
+
+logging.basicConfig(level=logging.ERROR, format="[%(levelname)s] %(message)s")
+logger = logging.getLogger(__name__)
+logger.setLevel(os.getenv("AGENT_RUNTIME_LOG_LEVEL", "INFO").upper())
+
+
+@tool
+def web_search(query: str) -> str:
+    """
+    Search the web for information using Tavily Search API.
+
+    Args:
+        query: The search query
+
+    Returns:
+        A string containing the search results
+    """
+    try:
+        # Get Tavily API key from environment variable
+        api_key = os.getenv("TAVILY_API_KEY")
+        if not api_key:
+            return "Error: TAVILY_API_KEY environment variable not set. Please sign up at https://tavily.com to get your API key."
+
+        tavily_client = TavilyClient(api_key=api_key)
+        response = tavily_client.search(query, max_results=5)
+
+        # Extract results from Tavily response
+        results = response.get("results", [])
+
+        formatted_results = []
+        for i, result in enumerate(results, 1):
+            formatted_results.append(
+                f"{i}. {result.get('title', 'No title')}\n"
+                f"   {result.get('content', 'No summary')}\n"
+                f"   Source: {result.get('url', 'No URL')}\n"
+            )
+
+        return "\n".join(formatted_results) if formatted_results else "No results found."
+
+    except Exception as e:
+        return f"Error searching the web: {str(e)}"
+
+
+@tool
+def web_search_ddg(query: str) -> str:
+    """
+    Search the web for information using DuckDuckGo Search.
+
+    Args:
+        query: The search query
+
+    Returns:
+        A string containing the search results
+    """
+    try:
+        # Initialize DuckDuckGo search client
+        ddgs = DDGS()
+
+        # Perform search with max_results=5
+        results = list(ddgs.text(query, max_results=5))
+
+        formatted_results = []
+        for i, result in enumerate(results, 1):
+            formatted_results.append(
+                f"{i}. {result.get('title', 'No title')}\n"
+                f"   {result.get('body', 'No summary')}\n"
+                f"   Source: {result.get('href', 'No URL')}\n"
+            )
+
+        return "\n".join(formatted_results) if formatted_results else "No results found."
+
+    except Exception as e:
+        return f"Error searching the web with DuckDuckGo: {str(e)}"
+
+
+@tool
+def country_specific_search(query: str) -> str:
+    """
+    Search for best places to visit in India with a 120-second delay before performing the search.
+    This tool waits for 2 minutes before executing a Tavily search about India travel destinations.
+
+    Args:
+        query: The search query (should be about best places to visit in India)
+
+    Returns:
+        A string containing the search results after the delay
+    """
+    try:
+        logger.info("Delayed India search initiated. Waiting 120 seconds before performing search...")
+
+        # Wait for 120 seconds
+        time.sleep(120)
+
+        logger.info("Wait complete. Performing Tavily search for India destinations...")
+
+        # Get Tavily API key from environment variable
+        api_key = os.getenv("TAVILY_API_KEY")
+        if not api_key:
+            return "Error: TAVILY_API_KEY environment variable not set. Please sign up at https://tavily.com to get your API key."
+
+        # Perform the search specifically about best places to visit in India
+        tavily_client = TavilyClient(api_key=api_key)
+        search_query = f"best places to visit in India {query}"
+        response = tavily_client.search(search_query, max_results=5)
+
+        # Extract results from Tavily response
+        results = response.get("results", [])
+
+        formatted_results = ["[DELAYED SEARCH - Waited 120 seconds before executing]\n"]
+        for i, result in enumerate(results, 1):
+            formatted_results.append(
+                f"{i}. {result.get('title', 'No title')}\n"
+                f"   {result.get('content', 'No summary')}\n"
+                f"   Source: {result.get('url', 'No URL')}\n"
+            )
+
+        return "\n".join(formatted_results) if len(formatted_results) > 1 else "No results found after delayed search."
+
+    except Exception as e:
+        return f"Error in delayed India search: {str(e)}"
+
+
+# Function to initialize Bedrock model
+def get_bedrock_model():
+    region = os.getenv("AWS_DEFAULT_REGION", "us-east-1")
+    model_id = os.getenv("BEDROCK_MODEL_ID", "us.anthropic.claude-3-5-sonnet-20240620-v1:0")
+
+    bedrock_model = BedrockModel(model_id=model_id, region_name=region, temperature=0.0, max_tokens=1024)
+    return bedrock_model
+
+
+# Initialize the Bedrock model
+bedrock_model = get_bedrock_model()
+
+
+# Define the agent's system prompt
+system_prompt = """You are an experienced travel agent specializing in personalized travel recommendations 
+with access to real-time web information from multiple search engines. Your role is to find dream destinations 
+matching user preferences by using BOTH available search tools to gather comprehensive information.
+
+IMPORTANT: When responding to queries:
+1. Use BOTH web_search (Tavily) and web_search_ddg (DuckDuckGo) tools for each query
+2. Clearly identify results from each search engine in your response
+3. Format your response to show:
+   - Results from Tavily Search (use web_search)
+   - Results from DuckDuckGo Search (use web_search_ddg)
+4. SPECIAL CASE: If someone asks specifically about "best places to visit in India", use the 
+   country_specific_search tool which will wait 120 seconds before performing a specialized Tavily search
+5. Synthesize information from both sources to provide comprehensive recommendations with current 
+   information, brief descriptions, and practical travel details."""
+
+
+app = BedrockAgentCoreApp()
+
+
+def initialize_agent():
+    """Initialize the agent with proper telemetry configuration."""
+
+    if OTEL_AVAILABLE:
+        try:
+            # Create a custom resource that respects OTEL_RESOURCE_ATTRIBUTES from environment
+            # This will automatically merge env vars with any explicit attributes
+            custom_resource = Resource.create(
+                attributes={
+                    "telemetry.sdk.name": "opentelemetry",
+                    "telemetry.sdk.language": "python",
+                }
+            )
+
+            # Create a custom tracer provider with our resource
+            tracer_provider = TracerProvider(resource=custom_resource)
+
+            # Set as global tracer provider (required for traces to work)
+            trace_api.set_tracer_provider(tracer_provider)
+
+            # Set up propagators (required for distributed tracing)
+            propagate.set_global_textmap(
+                CompositePropagator(
+                    [
+                        W3CBaggagePropagator(),
+                        TraceContextTextMapPropagator(),
+                    ]
+                )
+            )
+
+            # Initialize Strands telemetry with the custom tracer provider
+            strands_telemetry = StrandsTelemetry(tracer_provider=tracer_provider)
+            strands_telemetry.setup_otlp_exporter()
+
+            logger.info("Strands telemetry initialized with custom resource attributes")
+            logger.info(f"Resource attributes: {custom_resource.attributes}")
+        except Exception as e:
+            logger.warning("Telemetry setup failed: %s", str(e))
+    else:
+        logger.warning("Telemetry setup skipped - OpenTelemetry packages not available")
+
+    # Create and cache the agent
+    agent = Agent(
+        model=bedrock_model,
+        system_prompt=system_prompt,
+        tools=[web_search, web_search_ddg, country_specific_search],
+    )
+
+    return agent
+
+
+@app.entrypoint
+def strands_agent_bedrock(payload, context=None):
+    """
+    Invoke the agent with a payload
+    """
+    user_input = payload.get("prompt")
+    logger.info("[%s] User input: %s", context.session_id, user_input)
+
+    # Initialize agent with proper configuration
+    agent = initialize_agent()
+
+    response = agent(user_input)
+    return response.message["content"][0]["text"]
+
+
+if __name__ == "__main__":
+    app.run()
diff --git a/aws/amazon-bedrock-agentcore/travel_assistant/env.example b/aws/amazon-bedrock-agentcore/travel_assistant/env.example
new file mode 100644
index 0000000..c2014b3
--- /dev/null
+++ b/aws/amazon-bedrock-agentcore/travel_assistant/env.example
@@ -0,0 +1,49 @@
+# ===========================================
+# Travel Assistant Agent Configuration
+# ===========================================
+# Copy this file to .env and fill in your actual values
+
+# ============================================
+# REQUIRED: Tavily Search API Key
+# ============================================
+# Get your API key from: https://tavily.com
+TAVILY_API_KEY=your-tavily-api-key-here
+
+# ============================================
+# AWS Configuration
+# ============================================
+AWS_DEFAULT_REGION=us-east-1
+AWS_ACCESS_KEY_ID=your-aws-access-key
+AWS_SECRET_ACCESS_KEY=your-aws-secret-key
+BEDROCK_MODEL_ID=us.anthropic.claude-3-5-sonnet-20240620-v1:0
+
+# ============================================
+# Elastic Observability (Optional)
+# ============================================
+# Get these from your Elastic Cloud deployment
+# Documentation: https://cloud.elastic.co
+
+# OTLP Endpoint - Replace with your deployment ID and region
+OTEL_EXPORTER_OTLP_ENDPOINT=https://your-deployment-id.ingest.your-region.cloud.elastic.co:443
+
+# Elastic API Key - Replace with your actual API key
+OTEL_EXPORTER_OTLP_HEADERS=Authorization=ApiKey your-elastic-api-key-here
+
+# OpenTelemetry Configuration
+OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf
+OTEL_METRICS_EXPORTER=otlp
+OTEL_TRACES_EXPORTER=otlp
+OTEL_LOGS_EXPORTER=otlp
+
+# Resource Attributes - Customize as needed
+OTEL_RESOURCE_ATTRIBUTES=service.name=travel_assistant,service.version=1.0.0,deployment.environment=production
+
+# AgentCore Observability Flags
+AGENT_OBSERVABILITY_ENABLED=true
+DISABLE_ADOT_OBSERVABILITY=true
+
+# ============================================
+# Agent Configuration
+# ============================================
+AGENT_RUNTIME_LOG_LEVEL=INFO
+
diff --git a/aws/amazon-bedrock-agentcore/travel_assistant/invoke.sh b/aws/amazon-bedrock-agentcore/travel_assistant/invoke.sh
new file mode 100755
index 0000000..c8a1a98
--- /dev/null
+++ b/aws/amazon-bedrock-agentcore/travel_assistant/invoke.sh
@@ -0,0 +1,8 @@
+#!/bin/bash
+# Test script for regular search (no delay)
+# This will use both Tavily and DuckDuckGo search engines
+
+START=$(date +%s)
+agentcore invoke '{"prompt":"Best places to visit in Netherlands"}'
+END=$(date +%s)
+echo "Time taken: $((END - START)) seconds"
diff --git a/aws/amazon-bedrock-agentcore/travel_assistant/invoke_india_best_places.sh b/aws/amazon-bedrock-agentcore/travel_assistant/invoke_india_best_places.sh
new file mode 100755
index 0000000..5710371
--- /dev/null
+++ b/aws/amazon-bedrock-agentcore/travel_assistant/invoke_india_best_places.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# Test script for country-specific search with 120-second delay
+# This triggers the special India search tool
+
+START=$(date +%s)
+agentcore invoke '{"prompt":"Best places to visit in India"}'
+END=$(date +%s)
+echo "Time taken: $((END - START)) seconds"
+echo "Note: Expected time is 120+ seconds due to intentional delay"
diff --git a/aws/amazon-bedrock-agentcore/travel_assistant/launch_with_observability.sh b/aws/amazon-bedrock-agentcore/travel_assistant/launch_with_observability.sh
new file mode 100644
index 0000000..4a60a62
--- /dev/null
+++ b/aws/amazon-bedrock-agentcore/travel_assistant/launch_with_observability.sh
@@ -0,0 +1,16 @@
+#!/bin/bash
+# Launch script with full observability configuration
+# Make sure to replace placeholder values with your actual credentials
+
+agentcore launch \
+  --env OTEL_EXPORTER_OTLP_ENDPOINT="https://your-deployment-id.ingest.your-region.cloud.elastic.co:443" \
+  --env OTEL_EXPORTER_OTLP_HEADERS="Authorization=ApiKey your-elastic-api-key" \
+  --env OTEL_EXPORTER_OTLP_PROTOCOL="http/protobuf" \
+  --env OTEL_METRICS_EXPORTER="otlp" \
+  --env OTEL_TRACES_EXPORTER="otlp" \
+  --env OTEL_LOGS_EXPORTER="otlp" \
+  --env OTEL_RESOURCE_ATTRIBUTES="service.name=travel_assistant_quickstart,service.version=1.0.0,deployment.environment=production" \
+  --env AGENT_OBSERVABILITY_ENABLED="true" \
+  --env DISABLE_ADOT_OBSERVABILITY="true" \
+  --env TAVILY_API_KEY="your-tavily-api-key"
+
diff --git a/aws/amazon-bedrock-agentcore/travel_assistant/requirements.txt b/aws/amazon-bedrock-agentcore/travel_assistant/requirements.txt
new file mode 100644
index 0000000..c7fb0db
--- /dev/null
+++ b/aws/amazon-bedrock-agentcore/travel_assistant/requirements.txt
@@ -0,0 +1,9 @@
+bedrock-agentcore
+bedrock-agentcore-starter-toolkit
+strands-agents==1.17.0
+strands-agents-tools
+tavily-python
+duckduckgo-search
+opentelemetry-api
+opentelemetry-sdk
+opentelemetry-exporter-otlp-proto-http
\ No newline at end of file
diff --git a/langchainChat/langtrace-elastic-demo-readme.md b/langchainChat/langtrace-elastic-demo-readme.md
index 81e5042..bee3d86 100644
--- a/langchainChat/langtrace-elastic-demo-readme.md
+++ b/langchainChat/langtrace-elastic-demo-readme.md
@@ -75,7 +75,7 @@ Type 'quit' to exit the chat.
 
 ## Example Trace
 
-![Alt text](/langtrace/img/Xnapper-2024-08-16-12.36.03.png "Langtrace traces")
+![Alt text](img/Xnapper-2024-08-16-12.36.03.png "Langtrace traces")
 
 ## How it works